Upload folder using huggingface_hub

ft_7b_NLSY79_with_birth_year_ckpt_bo5/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "togethercomputer/llama-2-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

ft_7b_NLSY79_with_birth_year_ckpt_bo5/generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 32000,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.1"
+}

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59c04dcd4abaf5231c2cdbcdf71b46e395057165913f01365ee5b8c63d6f44b2
+size 4840396416

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9fa0ab1cb539c7b7e3b6bfe92999d8dd11facf95abbc1d5264dd1c201cd264a
+size 4857206856

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c1048ff016aa71804fd18bad1b71e56fe284a10e8e9027e7587aceab0dcd84b
+size 4857206904

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331ccadd53a9f2ffe668d235f02563f50cc1d441a7227698c352fd61c4d388c2
+size 4857206904

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01f1062d818454251752734c3e71df59a812704297408b495dcd8e6cfcc2e0e
+size 4857206904

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc08beb62d8575d07a5955456fd679a6169c1cfdbbc8e000a98110013c39bbb
+size 2684472112

ft_7b_NLSY79_with_birth_year_ckpt_bo5/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 26953662464
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

ft_7b_NLSY79_with_birth_year_ckpt_bo5/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

ft_7b_NLSY79_with_birth_year_ckpt_bo5/tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' or message['role'] == 'tool' %}{{ bos_token + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'system' %}{{ '<<SYS>>\\n' + content + '\\n<</SYS>>\\n\\n' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

ft_7b_NLSY79_with_birth_year_ckpt_bo5/trainer_state.json

@@ -0,0 +1,1123 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 30,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 11.48654842376709,
+      "learning_rate": 9.933333333333334e-06,
+      "loss": 1.0012,
+      "step": 1
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 5.478314399719238,
+      "learning_rate": 9.866666666666668e-06,
+      "loss": 0.7851,
+      "step": 2
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.208690166473389,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 0.4422,
+      "step": 3
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 5.6146368980407715,
+      "learning_rate": 9.733333333333334e-06,
+      "loss": 0.3538,
+      "step": 4
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 3.4289073944091797,
+      "learning_rate": 9.666666666666667e-06,
+      "loss": 0.2337,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.8489919900894165,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.1953,
+      "step": 6
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 3.0425381660461426,
+      "learning_rate": 9.533333333333334e-06,
+      "loss": 0.1877,
+      "step": 7
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.9351528882980347,
+      "learning_rate": 9.466666666666667e-06,
+      "loss": 0.1765,
+      "step": 8
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.198788046836853,
+      "learning_rate": 9.4e-06,
+      "loss": 0.173,
+      "step": 9
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.6411851048469543,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.1628,
+      "step": 10
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 0.6469910144805908,
+      "learning_rate": 9.266666666666667e-06,
+      "loss": 0.1686,
+      "step": 11
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.4584273099899292,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.1642,
+      "step": 12
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.4074181616306305,
+      "learning_rate": 9.133333333333335e-06,
+      "loss": 0.1542,
+      "step": 13
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.3630579710006714,
+      "learning_rate": 9.066666666666667e-06,
+      "loss": 0.1539,
+      "step": 14
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3679789900779724,
+      "learning_rate": 9e-06,
+      "loss": 0.1503,
+      "step": 15
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3458344638347626,
+      "learning_rate": 8.933333333333333e-06,
+      "loss": 0.1502,
+      "step": 16
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.3350043296813965,
+      "learning_rate": 8.866666666666668e-06,
+      "loss": 0.1448,
+      "step": 17
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.265071839094162,
+      "learning_rate": 8.8e-06,
+      "loss": 0.147,
+      "step": 18
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.23169605433940887,
+      "learning_rate": 8.733333333333333e-06,
+      "loss": 0.1472,
+      "step": 19
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.38610610365867615,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 0.1511,
+      "step": 20
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.3115122318267822,
+      "learning_rate": 8.6e-06,
+      "loss": 0.1432,
+      "step": 21
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.26815465092658997,
+      "learning_rate": 8.533333333333335e-06,
+      "loss": 0.1459,
+      "step": 22
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.2105124145746231,
+      "learning_rate": 8.466666666666668e-06,
+      "loss": 0.1422,
+      "step": 23
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.3036591112613678,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.1475,
+      "step": 24
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.29980674386024475,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.1434,
+      "step": 25
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.20851480960845947,
+      "learning_rate": 8.266666666666667e-06,
+      "loss": 0.1374,
+      "step": 26
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.3095088601112366,
+      "learning_rate": 8.2e-06,
+      "loss": 0.1395,
+      "step": 27
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.2337295413017273,
+      "learning_rate": 8.133333333333334e-06,
+      "loss": 0.1335,
+      "step": 28
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.2678751051425934,
+      "learning_rate": 8.066666666666667e-06,
+      "loss": 0.14,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.25164535641670227,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1419,
+      "step": 30
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.14010260999202728,
+      "eval_runtime": 2.6608,
+      "eval_samples_per_second": 49.985,
+      "eval_steps_per_second": 1.879,
+      "step": 30
+    },
+    {
+      "epoch": 1.0333333333333334,
+      "grad_norm": 0.22061151266098022,
+      "learning_rate": 7.933333333333334e-06,
+      "loss": 0.1421,
+      "step": 31
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.23729485273361206,
+      "learning_rate": 7.866666666666667e-06,
+      "loss": 0.1407,
+      "step": 32
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.20293913781642914,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 0.1358,
+      "step": 33
+    },
+    {
+      "epoch": 1.1333333333333333,
+      "grad_norm": 0.26370692253112793,
+      "learning_rate": 7.733333333333334e-06,
+      "loss": 0.1437,
+      "step": 34
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.20832230150699615,
+      "learning_rate": 7.666666666666667e-06,
+      "loss": 0.1334,
+      "step": 35
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.23263274133205414,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.14,
+      "step": 36
+    },
+    {
+      "epoch": 1.2333333333333334,
+      "grad_norm": 0.21567584574222565,
+      "learning_rate": 7.533333333333334e-06,
+      "loss": 0.1355,
+      "step": 37
+    },
+    {
+      "epoch": 1.2666666666666666,
+      "grad_norm": 0.20957590639591217,
+      "learning_rate": 7.4666666666666675e-06,
+      "loss": 0.14,
+      "step": 38
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.17557553946971893,
+      "learning_rate": 7.4e-06,
+      "loss": 0.1402,
+      "step": 39
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.208563894033432,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 0.1442,
+      "step": 40
+    },
+    {
+      "epoch": 1.3666666666666667,
+      "grad_norm": 0.17790338397026062,
+      "learning_rate": 7.266666666666668e-06,
+      "loss": 0.1378,
+      "step": 41
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.17678090929985046,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.1399,
+      "step": 42
+    },
+    {
+      "epoch": 1.4333333333333333,
+      "grad_norm": 0.18368814885616302,
+      "learning_rate": 7.133333333333334e-06,
+      "loss": 0.1325,
+      "step": 43
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 0.20683516561985016,
+      "learning_rate": 7.066666666666667e-06,
+      "loss": 0.134,
+      "step": 44
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.16159383952617645,
+      "learning_rate": 7e-06,
+      "loss": 0.1423,
+      "step": 45
+    },
+    {
+      "epoch": 1.5333333333333332,
+      "grad_norm": 0.1969640702009201,
+      "learning_rate": 6.9333333333333344e-06,
+      "loss": 0.1352,
+      "step": 46
+    },
+    {
+      "epoch": 1.5666666666666667,
+      "grad_norm": 0.18327245116233826,
+      "learning_rate": 6.866666666666667e-06,
+      "loss": 0.1422,
+      "step": 47
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.1710892915725708,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.1384,
+      "step": 48
+    },
+    {
+      "epoch": 1.6333333333333333,
+      "grad_norm": 0.1914682388305664,
+      "learning_rate": 6.733333333333334e-06,
+      "loss": 0.1302,
+      "step": 49
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.24561844766139984,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.1292,
+      "step": 50
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.15132392942905426,
+      "learning_rate": 6.600000000000001e-06,
+      "loss": 0.1279,
+      "step": 51
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.2071676403284073,
+      "learning_rate": 6.533333333333334e-06,
+      "loss": 0.1342,
+      "step": 52
+    },
+    {
+      "epoch": 1.7666666666666666,
+      "grad_norm": 0.1989034116268158,
+      "learning_rate": 6.466666666666667e-06,
+      "loss": 0.1366,
+      "step": 53
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.19416305422782898,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.1359,
+      "step": 54
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.19544005393981934,
+      "learning_rate": 6.333333333333333e-06,
+      "loss": 0.138,
+      "step": 55
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.19276417791843414,
+      "learning_rate": 6.266666666666668e-06,
+      "loss": 0.1353,
+      "step": 56
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.19002191722393036,
+      "learning_rate": 6.200000000000001e-06,
+      "loss": 0.1406,
+      "step": 57
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.17616640031337738,
+      "learning_rate": 6.133333333333334e-06,
+      "loss": 0.1311,
+      "step": 58
+    },
+    {
+      "epoch": 1.9666666666666668,
+      "grad_norm": 0.22256258130073547,
+      "learning_rate": 6.066666666666667e-06,
+      "loss": 0.1327,
+      "step": 59
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.19107486307621002,
+      "learning_rate": 6e-06,
+      "loss": 0.1363,
+      "step": 60
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.1355004608631134,
+      "eval_runtime": 2.7439,
+      "eval_samples_per_second": 48.47,
+      "eval_steps_per_second": 1.822,
+      "step": 60
+    },
+    {
+      "epoch": 2.033333333333333,
+      "grad_norm": 0.1652805656194687,
+      "learning_rate": 5.933333333333335e-06,
+      "loss": 0.1332,
+      "step": 61
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.1981014758348465,
+      "learning_rate": 5.8666666666666675e-06,
+      "loss": 0.1319,
+      "step": 62
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.1696314513683319,
+      "learning_rate": 5.8e-06,
+      "loss": 0.1344,
+      "step": 63
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.18335038423538208,
+      "learning_rate": 5.733333333333334e-06,
+      "loss": 0.132,
+      "step": 64
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.18856120109558105,
+      "learning_rate": 5.666666666666667e-06,
+      "loss": 0.1351,
+      "step": 65
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.20647232234477997,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.1349,
+      "step": 66
+    },
+    {
+      "epoch": 2.2333333333333334,
+      "grad_norm": 0.19078993797302246,
+      "learning_rate": 5.533333333333334e-06,
+      "loss": 0.1328,
+      "step": 67
+    },
+    {
+      "epoch": 2.2666666666666666,
+      "grad_norm": 0.27246996760368347,
+      "learning_rate": 5.466666666666667e-06,
+      "loss": 0.1311,
+      "step": 68
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 0.21068304777145386,
+      "learning_rate": 5.400000000000001e-06,
+      "loss": 0.1293,
+      "step": 69
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.20707523822784424,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 0.1351,
+      "step": 70
+    },
+    {
+      "epoch": 2.3666666666666667,
+      "grad_norm": 0.3069300055503845,
+      "learning_rate": 5.2666666666666665e-06,
+      "loss": 0.14,
+      "step": 71
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.20109064877033234,
+      "learning_rate": 5.2e-06,
+      "loss": 0.1346,
+      "step": 72
+    },
+    {
+      "epoch": 2.4333333333333336,
+      "grad_norm": 0.22994424402713776,
+      "learning_rate": 5.133333333333334e-06,
+      "loss": 0.1304,
+      "step": 73
+    },
+    {
+      "epoch": 2.466666666666667,
+      "grad_norm": 0.19537107646465302,
+      "learning_rate": 5.0666666666666676e-06,
+      "loss": 0.133,
+      "step": 74
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.18424610793590546,
+      "learning_rate": 5e-06,
+      "loss": 0.1299,
+      "step": 75
+    },
+    {
+      "epoch": 2.533333333333333,
+      "grad_norm": 0.21313366293907166,
+      "learning_rate": 4.933333333333334e-06,
+      "loss": 0.1387,
+      "step": 76
+    },
+    {
+      "epoch": 2.5666666666666664,
+      "grad_norm": 0.22169137001037598,
+      "learning_rate": 4.866666666666667e-06,
+      "loss": 0.1352,
+      "step": 77
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.1910381019115448,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 0.1302,
+      "step": 78
+    },
+    {
+      "epoch": 2.6333333333333333,
+      "grad_norm": 0.17845465242862701,
+      "learning_rate": 4.7333333333333335e-06,
+      "loss": 0.1344,
+      "step": 79
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.1703132688999176,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 0.1363,
+      "step": 80
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.2615348696708679,
+      "learning_rate": 4.600000000000001e-06,
+      "loss": 0.1314,
+      "step": 81
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.1989273577928543,
+      "learning_rate": 4.533333333333334e-06,
+      "loss": 0.1365,
+      "step": 82
+    },
+    {
+      "epoch": 2.7666666666666666,
+      "grad_norm": 0.21049782633781433,
+      "learning_rate": 4.4666666666666665e-06,
+      "loss": 0.1329,
+      "step": 83
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.2662608027458191,
+      "learning_rate": 4.4e-06,
+      "loss": 0.1404,
+      "step": 84
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.16182908415794373,
+      "learning_rate": 4.333333333333334e-06,
+      "loss": 0.1281,
+      "step": 85
+    },
+    {
+      "epoch": 2.8666666666666667,
+      "grad_norm": 0.15739159286022186,
+      "learning_rate": 4.266666666666668e-06,
+      "loss": 0.1342,
+      "step": 86
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.14015746116638184,
+      "learning_rate": 4.2000000000000004e-06,
+      "loss": 0.134,
+      "step": 87
+    },
+    {
+      "epoch": 2.9333333333333336,
+      "grad_norm": 0.1739162653684616,
+      "learning_rate": 4.133333333333333e-06,
+      "loss": 0.1352,
+      "step": 88
+    },
+    {
+      "epoch": 2.966666666666667,
+      "grad_norm": 0.17479591071605682,
+      "learning_rate": 4.066666666666667e-06,
+      "loss": 0.1306,
+      "step": 89
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.20147491991519928,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.1317,
+      "step": 90
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.13425087928771973,
+      "eval_runtime": 2.7506,
+      "eval_samples_per_second": 48.353,
+      "eval_steps_per_second": 1.818,
+      "step": 90
+    },
+    {
+      "epoch": 3.033333333333333,
+      "grad_norm": 0.17908453941345215,
+      "learning_rate": 3.9333333333333335e-06,
+      "loss": 0.1309,
+      "step": 91
+    },
+    {
+      "epoch": 3.066666666666667,
+      "grad_norm": 0.16888181865215302,
+      "learning_rate": 3.866666666666667e-06,
+      "loss": 0.1358,
+      "step": 92
+    },
+    {
+      "epoch": 3.1,
+      "grad_norm": 0.1876813769340515,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.1406,
+      "step": 93
+    },
+    {
+      "epoch": 3.1333333333333333,
+      "grad_norm": 0.20439200103282928,
+      "learning_rate": 3.7333333333333337e-06,
+      "loss": 0.1281,
+      "step": 94
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 0.14938826858997345,
+      "learning_rate": 3.6666666666666666e-06,
+      "loss": 0.1293,
+      "step": 95
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.22059953212738037,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 0.1347,
+      "step": 96
+    },
+    {
+      "epoch": 3.2333333333333334,
+      "grad_norm": 0.1910008192062378,
+      "learning_rate": 3.5333333333333335e-06,
+      "loss": 0.1326,
+      "step": 97
+    },
+    {
+      "epoch": 3.2666666666666666,
+      "grad_norm": 0.14996027946472168,
+      "learning_rate": 3.4666666666666672e-06,
+      "loss": 0.135,
+      "step": 98
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.16143576800823212,
+      "learning_rate": 3.4000000000000005e-06,
+      "loss": 0.1256,
+      "step": 99
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.1857629120349884,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.1309,
+      "step": 100
+    },
+    {
+      "epoch": 3.3666666666666667,
+      "grad_norm": 0.22081272304058075,
+      "learning_rate": 3.266666666666667e-06,
+      "loss": 0.1257,
+      "step": 101
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.1734398752450943,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 0.1353,
+      "step": 102
+    },
+    {
+      "epoch": 3.4333333333333336,
+      "grad_norm": 0.19134736061096191,
+      "learning_rate": 3.133333333333334e-06,
+      "loss": 0.1304,
+      "step": 103
+    },
+    {
+      "epoch": 3.466666666666667,
+      "grad_norm": 0.19944500923156738,
+      "learning_rate": 3.066666666666667e-06,
+      "loss": 0.133,
+      "step": 104
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.1744658201932907,
+      "learning_rate": 3e-06,
+      "loss": 0.1267,
+      "step": 105
+    },
+    {
+      "epoch": 3.533333333333333,
+      "grad_norm": 0.15133057534694672,
+      "learning_rate": 2.9333333333333338e-06,
+      "loss": 0.1283,
+      "step": 106
+    },
+    {
+      "epoch": 3.5666666666666664,
+      "grad_norm": 0.16132541000843048,
+      "learning_rate": 2.866666666666667e-06,
+      "loss": 0.1333,
+      "step": 107
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 0.1777673214673996,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 0.1281,
+      "step": 108
+    },
+    {
+      "epoch": 3.6333333333333333,
+      "grad_norm": 0.14122550189495087,
+      "learning_rate": 2.7333333333333336e-06,
+      "loss": 0.128,
+      "step": 109
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.14310942590236664,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 0.1335,
+      "step": 110
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.15641361474990845,
+      "learning_rate": 2.6e-06,
+      "loss": 0.1314,
+      "step": 111
+    },
+    {
+      "epoch": 3.7333333333333334,
+      "grad_norm": 0.14074623584747314,
+      "learning_rate": 2.5333333333333338e-06,
+      "loss": 0.1352,
+      "step": 112
+    },
+    {
+      "epoch": 3.7666666666666666,
+      "grad_norm": 0.14279833436012268,
+      "learning_rate": 2.466666666666667e-06,
+      "loss": 0.1355,
+      "step": 113
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.15949110686779022,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.1388,
+      "step": 114
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 0.165536031126976,
+      "learning_rate": 2.3333333333333336e-06,
+      "loss": 0.1356,
+      "step": 115
+    },
+    {
+      "epoch": 3.8666666666666667,
+      "grad_norm": 0.13657666742801666,
+      "learning_rate": 2.266666666666667e-06,
+      "loss": 0.13,
+      "step": 116
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.17128072679042816,
+      "learning_rate": 2.2e-06,
+      "loss": 0.1362,
+      "step": 117
+    },
+    {
+      "epoch": 3.9333333333333336,
+      "grad_norm": 0.14848357439041138,
+      "learning_rate": 2.133333333333334e-06,
+      "loss": 0.1276,
+      "step": 118
+    },
+    {
+      "epoch": 3.966666666666667,
+      "grad_norm": 0.1311183124780655,
+      "learning_rate": 2.0666666666666666e-06,
+      "loss": 0.1267,
+      "step": 119
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12412682920694351,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.1253,
+      "step": 120
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.13342367112636566,
+      "eval_runtime": 2.7606,
+      "eval_samples_per_second": 48.178,
+      "eval_steps_per_second": 1.811,
+      "step": 120
+    },
+    {
+      "epoch": 4.033333333333333,
+      "grad_norm": 0.13110075891017914,
+      "learning_rate": 1.9333333333333336e-06,
+      "loss": 0.1294,
+      "step": 121
+    },
+    {
+      "epoch": 4.066666666666666,
+      "grad_norm": 0.1533585786819458,
+      "learning_rate": 1.8666666666666669e-06,
+      "loss": 0.1337,
+      "step": 122
+    },
+    {
+      "epoch": 4.1,
+      "grad_norm": 0.12748676538467407,
+      "learning_rate": 1.8000000000000001e-06,
+      "loss": 0.1271,
+      "step": 123
+    },
+    {
+      "epoch": 4.133333333333334,
+      "grad_norm": 0.1390267312526703,
+      "learning_rate": 1.7333333333333336e-06,
+      "loss": 0.1266,
+      "step": 124
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 0.1537020206451416,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.1329,
+      "step": 125
+    },
+    {
+      "epoch": 4.2,
+      "grad_norm": 0.14931295812129974,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 0.1305,
+      "step": 126
+    },
+    {
+      "epoch": 4.233333333333333,
+      "grad_norm": 0.15617649257183075,
+      "learning_rate": 1.5333333333333334e-06,
+      "loss": 0.1263,
+      "step": 127
+    },
+    {
+      "epoch": 4.266666666666667,
+      "grad_norm": 0.14233970642089844,
+      "learning_rate": 1.4666666666666669e-06,
+      "loss": 0.1387,
+      "step": 128
+    },
+    {
+      "epoch": 4.3,
+      "grad_norm": 0.13745148479938507,
+      "learning_rate": 1.4000000000000001e-06,
+      "loss": 0.1325,
+      "step": 129
+    },
+    {
+      "epoch": 4.333333333333333,
+      "grad_norm": 0.16146665811538696,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.1251,
+      "step": 130
+    },
+    {
+      "epoch": 4.366666666666666,
+      "grad_norm": 0.13990050554275513,
+      "learning_rate": 1.2666666666666669e-06,
+      "loss": 0.1343,
+      "step": 131
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.15942668914794922,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.127,
+      "step": 132
+    },
+    {
+      "epoch": 4.433333333333334,
+      "grad_norm": 0.13994060456752777,
+      "learning_rate": 1.1333333333333334e-06,
+      "loss": 0.1277,
+      "step": 133
+    },
+    {
+      "epoch": 4.466666666666667,
+      "grad_norm": 0.14793553948402405,
+      "learning_rate": 1.066666666666667e-06,
+      "loss": 0.1303,
+      "step": 134
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.1624802052974701,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.1311,
+      "step": 135
+    },
+    {
+      "epoch": 4.533333333333333,
+      "grad_norm": 0.15695539116859436,
+      "learning_rate": 9.333333333333334e-07,
+      "loss": 0.1322,
+      "step": 136
+    },
+    {
+      "epoch": 4.566666666666666,
+      "grad_norm": 0.1207505464553833,
+      "learning_rate": 8.666666666666668e-07,
+      "loss": 0.1328,
+      "step": 137
+    },
+    {
+      "epoch": 4.6,
+      "grad_norm": 0.1304347962141037,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 0.1341,
+      "step": 138
+    },
+    {
+      "epoch": 4.633333333333333,
+      "grad_norm": 0.14322949945926666,
+      "learning_rate": 7.333333333333334e-07,
+      "loss": 0.1335,
+      "step": 139
+    },
+    {
+      "epoch": 4.666666666666667,
+      "grad_norm": 0.1278732270002365,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 0.1356,
+      "step": 140
+    },
+    {
+      "epoch": 4.7,
+      "grad_norm": 0.1423725187778473,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.1256,
+      "step": 141
+    },
+    {
+      "epoch": 4.733333333333333,
+      "grad_norm": 0.12826520204544067,
+      "learning_rate": 5.333333333333335e-07,
+      "loss": 0.1313,
+      "step": 142
+    },
+    {
+      "epoch": 4.766666666666667,
+      "grad_norm": 0.13897734880447388,
+      "learning_rate": 4.666666666666667e-07,
+      "loss": 0.1332,
+      "step": 143
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.1477193683385849,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 0.1286,
+      "step": 144
+    },
+    {
+      "epoch": 4.833333333333333,
+      "grad_norm": 0.13287104666233063,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 0.1276,
+      "step": 145
+    },
+    {
+      "epoch": 4.866666666666667,
+      "grad_norm": 0.13120640814304352,
+      "learning_rate": 2.666666666666667e-07,
+      "loss": 0.1274,
+      "step": 146
+    },
+    {
+      "epoch": 4.9,
+      "grad_norm": 0.1554274559020996,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 0.1261,
+      "step": 147
+    },
+    {
+      "epoch": 4.933333333333334,
+      "grad_norm": 0.12639135122299194,
+      "learning_rate": 1.3333333333333336e-07,
+      "loss": 0.1259,
+      "step": 148
+    },
+    {
+      "epoch": 4.966666666666667,
+      "grad_norm": 0.12116540968418121,
+      "learning_rate": 6.666666666666668e-08,
+      "loss": 0.1297,
+      "step": 149
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.12108778953552246,
+      "learning_rate": 0.0,
+      "loss": 0.1278,
+      "step": 150
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.13310247659683228,
+      "eval_runtime": 2.7327,
+      "eval_samples_per_second": 48.671,
+      "eval_steps_per_second": 1.83,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 30,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.715663693361971e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}